<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-05490235</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-25T03:52:52+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Adaptive Dirichlet Process mixture model with unknown concentration parameter and variance: Scaling high dimensional clustering via collapsed variational inference</title>
            <author role="aut">
              <persName>
                <forename type="first">Annesh</forename>
                <surname>Pal</surname>
              </persName>
              <idno type="halauthorid">4015509-0</idno>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-220073"/>
              <affiliation ref="#struct-476572"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Aguirre</forename>
                <surname>Mimoun</surname>
              </persName>
              <idno type="halauthorid">3042462-0</idno>
              <affiliation ref="#struct-300122"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Rodolphe</forename>
                <surname>Thiébaut</surname>
              </persName>
              <email type="md5">242f217052cdd1b15e9288ab507c175b</email>
              <email type="domain">u-bordeaux.fr</email>
              <idno type="idhal" notation="string">rodolphe-thiebaut</idno>
              <idno type="idhal" notation="numeric">175125</idno>
              <idno type="halauthorid" notation="string">32082-175125</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-5235-3962</idno>
              <idno type="IDREF">https://www.idref.fr/071580735</idno>
              <affiliation ref="#struct-300122"/>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-476572"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Boris P.</forename>
                <surname>Hejblum</surname>
              </persName>
              <email type="md5">00e5ae285f2288acc3ba52b6b4c3ff1b</email>
              <email type="domain">u-bordeaux.fr</email>
              <idno type="idhal" notation="string">boris-hejblum</idno>
              <idno type="idhal" notation="numeric">10465</idno>
              <idno type="halauthorid" notation="string">29388-10465</idno>
              <idno type="ARXIV">https://arxiv.org/a/hejblum_b_1</idno>
              <idno type="ORCID">https://orcid.org/0000-0003-0646-452X</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=xU72YmYAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/189970316</idno>
              <affiliation ref="#struct-219689"/>
              <affiliation ref="#struct-220073"/>
              <affiliation ref="#struct-476572"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Boris</forename>
                <surname>Hejblum</surname>
              </persName>
              <email type="md5">00e5ae285f2288acc3ba52b6b4c3ff1b</email>
              <email type="domain">u-bordeaux.fr</email>
            </editor>
            <funder ref="#projanr-98257"/>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2026-02-03 00:22:22</date>
              <date type="whenWritten">2026-01-28</date>
              <date type="whenModified">2026-02-07 03:22:13</date>
              <date type="whenReleased">2026-02-03 11:51:40</date>
              <date type="whenProduced">2026-01-28</date>
              <date type="whenEndEmbargoed">2026-02-03</date>
              <ref type="file" target="https://inria.hal.science/hal-05490235v1/document">
                <date notBefore="2026-02-03"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://inria.hal.science/hal-05490235v1/file/2601.21106v1.pdf" id="file-5490235-4699530">
                <date notBefore="2026-02-03"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2601.21106"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="557959">
                <persName>
                  <forename>Boris</forename>
                  <surname>Hejblum</surname>
                </persName>
                <email type="md5">00e5ae285f2288acc3ba52b6b4c3ff1b</email>
                <email type="domain">u-bordeaux.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05490235</idno>
            <idno type="halUri">https://inria.hal.science/hal-05490235</idno>
            <idno type="halBibtex">pal:hal-05490235</idno>
            <idno type="halRefHtml">2026</idno>
            <idno type="halRef">2026</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-sa/4.0/">CC BY-SA 4.0 - Attribution - ShareAlike<ref corresp="#file-5490235-4699530"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="INRIA">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="INRIA-BORDEAUX">INRIA Bordeaux - Sud-Ouest</idno>
            <idno type="stamp" n="SANTE_PUB_INSERM" corresp="INSERM">Santé Publique à l'Inserm</idno>
            <idno type="stamp" n="INRIA_TEST">INRIA - Institut National de Recherche en Informatique et en Automatique</idno>
            <idno type="stamp" n="UPEC" corresp="CV_UPEC">Université Paris-Est Créteil Val-de-Marne</idno>
            <idno type="stamp" n="TESTALAIN1">TESTALAIN1</idno>
            <idno type="stamp" n="TESTBORDEAUX">TESTBORDEAUX</idno>
            <idno type="stamp" n="INRIA2">INRIA 2</idno>
            <idno type="stamp" n="ANR">ANR</idno>
            <idno type="stamp" n="U1219" corresp="INSERM">Bordeaux Population Health</idno>
            <idno type="stamp" n="PEPR_SANTENUM">PEPR Santé numérique</idno>
            <idno type="stamp" n="UNIVERSITE-BORDEAUX">Université de Bordeaux</idno>
            <idno type="stamp" n="TEST-UPEC-ODD" corresp="UPEC">TEST UPEC ODD</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Adaptive Dirichlet Process mixture model with unknown concentration parameter and variance: Scaling high dimensional clustering via collapsed variational inference</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Annesh</forename>
                    <surname>Pal</surname>
                  </persName>
                  <idno type="halauthorid">4015509-0</idno>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-220073"/>
                  <affiliation ref="#struct-476572"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Aguirre</forename>
                    <surname>Mimoun</surname>
                  </persName>
                  <idno type="halauthorid">3042462-0</idno>
                  <affiliation ref="#struct-300122"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Rodolphe</forename>
                    <surname>Thiébaut</surname>
                  </persName>
                  <email type="md5">242f217052cdd1b15e9288ab507c175b</email>
                  <email type="domain">u-bordeaux.fr</email>
                  <idno type="idhal" notation="string">rodolphe-thiebaut</idno>
                  <idno type="idhal" notation="numeric">175125</idno>
                  <idno type="halauthorid" notation="string">32082-175125</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-5235-3962</idno>
                  <idno type="IDREF">https://www.idref.fr/071580735</idno>
                  <affiliation ref="#struct-300122"/>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-476572"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Boris P.</forename>
                    <surname>Hejblum</surname>
                  </persName>
                  <email type="md5">00e5ae285f2288acc3ba52b6b4c3ff1b</email>
                  <email type="domain">u-bordeaux.fr</email>
                  <idno type="idhal" notation="string">boris-hejblum</idno>
                  <idno type="idhal" notation="numeric">10465</idno>
                  <idno type="halauthorid" notation="string">29388-10465</idno>
                  <idno type="ARXIV">https://arxiv.org/a/hejblum_b_1</idno>
                  <idno type="ORCID">https://orcid.org/0000-0003-0646-452X</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.com/citations?user=xU72YmYAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/189970316</idno>
                  <affiliation ref="#struct-219689"/>
                  <affiliation ref="#struct-220073"/>
                  <affiliation ref="#struct-476572"/>
                </author>
              </analytic>
              <monogr>
                <imprint>
                  <date type="datePub">2026-01-28</date>
                </imprint>
              </monogr>
              <idno type="arxiv">2601.21106</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Bayesian Nonparametrics</term>
                <term xml:lang="en">Clustering</term>
                <term xml:lang="en">Dirichlet process mixture model</term>
                <term xml:lang="en">Variational inference</term>
                <term xml:lang="en">Unstructured covariance</term>
                <term xml:lang="en">Concentration parameter</term>
                <term xml:lang="en">High-dimension</term>
                <term xml:lang="en">Gene expression data</term>
              </keywords>
              <classCode scheme="halDomain" n="sdv.bibs">Life Sciences [q-bio]/Quantitative Methods [q-bio.QM]</classCode>
              <classCode scheme="halDomain" n="sdv.spee">Life Sciences [q-bio]/Santé publique et épidémiologie</classCode>
              <classCode scheme="halDomain" n="stat.me">Statistics [stat]/Methodology [stat.ME]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>We propose a novel method that performs adaptive clustering with DPMM using collapsed VI, while incorporating weakly-informative priors for DP concentration parameter alpha and base distribution G0. We illustrate the importance of G0 covariance structure and prior choice by considering different parameterisations of the data covariance matrix. On high-dimensional Gaussian simulations, our model demonstrates substantially faster convergence than a state-of-the-art MCMC splice sampler. We further evaluate performances on Negative Binomial simulations and conduct sensitivity analyses to assess robustness on realistic data conditions. Application to a publicly available leukemia transcriptomic data set comprising 72 samples and 2,194 gene expression successfully recovers every known sub-type, all while identifying additional gene expression-based sub-clusters with meaningful biological interpretation.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-219689" status="VALID">
          <idno type="RNSR">201321095C</idno>
          <idno type="ROR">https://ror.org/026t7px13</idno>
          <orgName>Statistics In System biology and Translational Medicine</orgName>
          <orgName type="acronym">SISTM</orgName>
          <date type="start">2016-01-01</date>
          <date type="end">2027-12-31</date>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour 33405 Talence cedex 146 Rue Léo Saignat33076 Bordeaux cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/equipes/sistm</ref>
          </desc>
          <listRelation>
            <relation active="#struct-104751" type="direct"/>
            <relation active="#struct-300009" type="indirect"/>
            <relation active="#struct-476572" type="direct"/>
            <relation active="#struct-259761" type="indirect"/>
            <relation active="#struct-302259" type="indirect"/>
            <relation name="U1219" active="#struct-303623" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-220073" status="VALID">
          <orgName>Vaccine Research Institute [Créteil, France]</orgName>
          <orgName type="acronym">VRI</orgName>
          <desc>
            <address>
              <addrLine>61 avenue du Général de Gaulle 94010 Créteil Cedex France</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.recherche-vaccinvih.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-420786" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-476572" status="VALID">
          <idno type="IdRef">197398162</idno>
          <idno type="RNSR">201622170H</idno>
          <idno type="ROR">https://ror.org/00xzzba89</idno>
          <orgName>Bordeaux population health</orgName>
          <orgName type="acronym">BPH</orgName>
          <desc>
            <address>
              <addrLine>Université de Bordeaux - Case 11 - 146 rue Léo Saignat  33076 Bordeaux cedex</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-259761" type="direct"/>
            <relation active="#struct-302259" type="direct"/>
            <relation name="U1219" active="#struct-303623" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300122" status="VALID">
          <idno type="IdRef">028228421</idno>
          <idno type="ROR">https://ror.org/01hq89f96</idno>
          <orgName>Centre Hospitalier Universitaire de Bordeaux</orgName>
          <orgName type="acronym">CHU Bordeaux</orgName>
          <desc>
            <address>
              <addrLine>12 rue Dubernat 33400 Talence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.chu-bordeaux.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-104751" status="VALID">
          <idno type="RNSR">200818243Z</idno>
          <idno type="ROR">https://ror.org/03tjcj052</idno>
          <orgName>Centre Inria de l'Université de Bordeaux</orgName>
          <desc>
            <address>
              <addrLine>200, avenue de la Vieille Tour, 33405 Talence</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/bordeaux/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300009" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-300009" status="VALID">
          <idno type="ROR">https://ror.org/02kvxyf05</idno>
          <orgName>Institut National de Recherche en Informatique et en Automatique</orgName>
          <orgName type="acronym">Inria</orgName>
          <desc>
            <address>
              <addrLine>Domaine de VoluceauRocquencourt - BP 10578153 Le Chesnay Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inria.fr/en/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-259761" status="VALID">
          <idno type="IdRef">175206562</idno>
          <idno type="ROR">https://ror.org/057qpr032</idno>
          <orgName>Université de Bordeaux</orgName>
          <orgName type="acronym">UB</orgName>
          <desc>
            <address>
              <addrLine>35, place Pey Berland - 33076 Bordeaux</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-bordeaux.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302259" status="VALID">
          <orgName>Institut de Santé Publique, d'Épidémiologie et de Développement (ISPED)</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303623" status="VALID">
          <idno type="IdRef">026388278</idno>
          <idno type="ROR">https://ror.org/02vjkv261</idno>
          <orgName>Institut National de la Santé et de la Recherche Médicale</orgName>
          <orgName type="acronym">INSERM</orgName>
          <desc>
            <address>
              <addrLine>101, rue de Tolbiac, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inserm.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-420786" status="VALID">
          <idno type="IdRef">028021037</idno>
          <idno type="ISNI">0000000121497878</idno>
          <idno type="ROR">https://ror.org/05ggc9x40</idno>
          <orgName>Université Paris-Est Créteil Val-de-Marne - Paris 12</orgName>
          <orgName type="acronym">UPEC UP12</orgName>
          <date type="start">1970-01-01</date>
          <desc>
            <address>
              <addrLine>61 avenue du Général de Gaulle - 94010 Créteil cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.u-pec.fr/</ref>
          </desc>
        </org>
      </listOrg>
      <listOrg type="projects">
        <org type="anrProject" xml:id="projanr-98257" status="VALID">
          <idno type="anr">ANR-22-PESN-0003</idno>
          <orgName>SMATCH</orgName>
          <desc>Statistical and AI based Methods for Advanced Clinical Trial CHallenges in Digital Health</desc>
          <date type="start">2022</date>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>